© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108412
    Prev
    Next
    INDEX
    Explanations

    Measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å²ģ以ä¸Ĭ
    -0.27
     ör
    -0.27
    ovan
    -0.26
    éĢļ讯åijĺ
    -0.26
    è£Ķ
    -0.26
    annah
    -0.24
    -<?
    -0.23
    æĹłéĻIJ
    -0.23
     życia
    -0.23
    /<?
    -0.23
    POSITIVE LOGITS
     magnitude
    0.71
    æķ°éĩı
    0.66
     quantity
    0.66
    çļĦæķ°éĩı
    0.63
    magnitude
    0.60
     timing
    0.59
    quantity
    0.56
     Quantity
    0.55
    è´¨éĩıåĴĮ
    0.52
    timing
    0.51
    Activations Density 1.001%

    No Known Activations